Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Open Journal of Signal Processing Année : 2023

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

Résumé

In this article, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exhaustively compare both methods for six model architectures, three complex-valued, and their respective real-equivalent models. We are comparing, therefore, not only the input representation impact but also the complex-against the real-valued models. We then argue that the dataset splitting produces a high correlation between training and validation sets, saturating the task and thus achieving very high performance. We, therefore, use a different data pre-processing technique designed to reduce this effect and reproduce the results with the same configurations as before (input representation and model architectures). After seeing that the performance per class is highly different according to class occurrences, we propose two methods for reducing this gap and performing the results for all input representations, models, and dataset pre-processing.
Fichier principal
Vignette du fichier
demr22072.pdf (1.71 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04052466 , version 1 (30-03-2023)

Identifiants

Citer

Jose Agustin Barrachina, Chengfang Ren, Christéle Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez. Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks. IEEE Open Journal of Signal Processing, 2023, 4, pp.157-166. ⟨10.1109/OJSP.2023.3246391⟩. ⟨hal-04052466⟩
11 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More